Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2605.10851v2 Announce Type: replace Abstract: We initiate the study of the Generalized Turing Test (GTT), a formal generalization of Turing's imitation game from humans to arbitrary interactive...
arXiv:2609.32259v2 Announce Type: replace Abstract: Recent multi-agent LLM systems increasingly combine heterogeneous models for specialized agent roles. However, text-based communication requires ea...
arXiv:2609.38816v1 Announce Type: new Abstract: While multi-agent and model collaboration algorithms gain traction to combine the strengths of diverse Large Language Models (LLMs), existing systems r...
arXiv:2609.39001v1 Announce Type: cross Abstract: LLM services are billed per token and context windows are measured in tokens, yet the number of tokens needed for the same content varies across lang...
arXiv:2609.39765v1 Announce Type: new Abstract: Agent memory faces heterogeneous access needs: a single-hop question may require one piece of evidence, whereas a multi-hop question must combine evide...
arXiv:2609.40097v1 Announce Type: new Abstract: Existing auto-research benchmarks often entangle multiple sources of improvement, including training frameworks, hyperparameters, compute budgets, and...
arXiv:2609.38324v1 Announce Type: cross Abstract: Multi-agent systems of LLMs add discussion to majority voting and are therefore expected to be more capable. However, empirical reports conflict on w...
SecureVibe is a training recipe designed to enhance the security of vibe coding by explicitly targeting planning and testing for code security. It combines supervised fine‑tuning on a security suite with post‑training methods (SECUREVIBE_rl and SECUREVIBE_hg) that use verifiable execution feedback and hint‑based self‑supervision. The approach outperforms baselines on multiple security coding benchmarks, improving security pass@1 by up to 6.9 points on BaxBench and 11.5 points on SusVibes, while also boosting functionality pass@1 on both security and generic coding tasks.
arXiv:2609.39050v1 Announce Type: cross Abstract: As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has e...
arXiv:2609.39333v1 Announce Type: cross Abstract: Autonomous AI agents can turn authors' goals into interactive narratives by independently organizing and carrying out generation and revision. As age...
arXiv:2609.39549v1 Announce Type: cross Abstract: As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant secu...
arXiv:2606.15911v2 Announce Type: replace Abstract: This paper focuses on automatically generating informative ad descriptions in sponsored search. Unlike ad titles which are usually optimized to att...
arXiv:2606.20487v2 Announce Type: replace Abstract: Computer use agents are expanding from single-device operation toward cross-device systems that coordinate tasks across heterogeneous environments....
arXiv:2608.03239v2 Announce Type: replace Abstract: Large language model-based multi-agent systems (LLM-MAS) are designed through roles, debate protocols, and aggregation rules. These choices create...
arXiv:2609.33676v2 Announce Type: replace Abstract: LLM agents increasingly take consequential actions through interactions with users, policies, and external tools. Auditing these agents requires au...
A2Z GameSpec-Bench introduces a benchmark of 100 long‑form Game Design Documents (GDDs) to evaluate how faithfully coding agents can generate complete games from detailed specifications. The benchmark measures faithfulness by checking that the game satisfies the GDD requirements and preserves the relationships among them, using a dependency‑aware contract and a combination of source‑code inspection and agent‑generated test policies. Evaluations show that current agents struggle to meet interdependent requirements, but requirement‑specific feedback improves GDD fidelity by 10.9% after two revision rounds.
DyRAD introduces a novel radar novel‑view synthesis framework that models dynamic driving scenes by separating static background reflectors from motion‑tracked dynamic point reflectors, enabling the rendering of full range‑azimuth‑Doppler (RAD) tensors. The method derives reflector velocities from object tracks, projects them onto the line of sight, and uses a fixed analytic point‑spread function to avoid embedding sensor‑induced spread into the scene representation. This design allows accurate scene reconstruction and zero‑shot transfer to different radar configurations, achieving a 90.7% recovery of radar detections on the RADIal dataset compared to 26.9% for the best baseline.
The paper introduces Trajectory-guided Joint Policy Optimization (TJPO), a reinforcement‑learning framework that explicitly encourages diversity in the trajectories of large‑language‑model agents. By defining task‑specific trajectory descriptors, TJPO measures and optimizes diversity as a set‑level function, avoiding population‑based training. Experiments on Sokoban and ALFWorld demonstrate that TJPO yields diverse, interpretable behaviors while preserving strong task performance.
arXiv:2504.04711v2 Announce Type: replace Abstract: Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of abstraction that impedes defin...
The paper introduces Harness Primitives—reusable agent harness mechanisms mined from failed task trajectories—and a framework called STITCH that selects and composes these primitives into task‑specific harnesses at test time. This approach avoids generating or debugging harness code for each task, achieving up to 12‑point gains in task success over fixed harness baselines and outperforming human‑designed harnesses like Codex CLI. STITCH also demonstrates minimal test‑time overhead (2.7%) and scales efficiently with the size of the primitive library.